非负矩阵分解法在化探数据处理中的应用  

Application of Non-Negative Matrix Factorization in Rock Geochemical Data Processing

作　　者：杨震[1] 梅红波[1] 杨明国[1] 

机构地区：[1]中国地质大学资源学院,湖北武汉430074

出　　处：《安徽理工大学学报（自然科学版）》2017年第2期44-50,共7页Journal of Anhui University of Science and Technology:Natural Science

基　　金：云南省三年找矿行动计划整装勘查项目基金资助(Z201010)

摘　　要：岩石地球化学数据均为非负数值,可以用非负矩阵来表示,这使得利用非负矩阵分解(NMF)方法处理该类数据成为可能。介绍了非负矩阵分解方法的基本原理,探讨了基于非负矩阵分解方法处理岩石地球化学数据的可能性和效果。以个旧陡岩地区岩石地球化学数据为例,分别运用NMF方法和主成分分析方法(PCA)对其进行异常提取,并对两种方法的处理结果进行对比分析,发现NMF方法是一种有效的处理岩石地球化学数据的方法。尽管这两种方法各自有其优越性,但就本实例数据而言,NMF方法优于PCA方法。This paper explores the possibility of applying non- negative matrix faetorization （NMF） to process rock geochemical data for mineral exploration. The brief introduction of the principle of NMF is followed by de- tailed comparison of the results obtained by NMF and principal component analysis （PCA） applied to a dataset of 1010 samples with 7 trace elements from Douyan area, Gejiu, Yunnan, China. It shows that the NMF is not only suitable for processing geochemical data which are usually of positive values but also provides better results than that by PCA in the case study introduced in the paper. The example indicates that NMF might become a useful method for processing other types of geochemical data.

关 键 词：非负矩阵分解 主成分分析 岩石地球化学数据 陡岩地区 

分 类 号：P628[天文地球—地质矿产勘探]